© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 47572
    Prev
    Next
    INDEX
    Explanations

    on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unui
    -0.08
     Into
    -0.08
     gemeins
    -0.08
     Dangerous
    -0.08
     Forgotten
    -0.08
     një
    -0.08
     WRONG
    -0.08
     Binary
    -0.08
    into
    -0.08
     Uph
    -0.07
    POSITIVE LOGITS
     hand
    0.22
    hand
    0.18
    -hand
    0.18
    Hand
    0.17
     Hand
    0.16
    _hand
    0.16
     standby
    0.16
    (hand
    0.15
     voljo
    0.15
     deck
    0.14
    Activations Density 0.014%

    No Known Activations